I don't think it will help. Actual friends occasionally send me mail that says "test" from a random account. And spammers do too... There is no way to seperate them.

Personally I haven’t had that problem. I can readily distinguish spam from non-spam by manual review ~99% of the time. If I could train or instruct an LLM to do the same as I do now, I would be happy. My current false-negative rate with Bayesian spamassassin is more like 50%.

Don't you do it somehow? Plus a filter doesn't have to be 100% right all the time. Filtering out what is 99% certain to be or not be spam and leaving the human to cover the tiny number of messages that fall into a grey area would still save a ton of time.

Yes, but I rely on my own personal experiences (online and offline) to determine whether an email is real or a scam. Unless that AI filter taps into my memory, it will likely lead to too many false positives and false negatives.